Supervised Learning for Untangling Braids

Alexei Lisitsa, Mateo Salles, Alexei Vernitski

2023

Abstract

Untangling a braid is a typical multi-step process, and reinforcement learning can be used to train an agent to untangle braids. Here we present another approach. Starting from the untangled braid, we produce a dataset of braids using breadth-first search and then apply behavioral cloning to train an agent on the output of this search. As a result, the (inverses of) steps predicted by the agent turn out to be an unexpectedly good method of untangling braids, including those braids which did not feature in the dataset.

Paper Citation

in Harvard Style

Lisitsa A., Salles M. and Vernitski A. (2023). Supervised Learning for Untangling Braids. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 784-789. DOI: 10.5220/0011775900003393

in Bibtex Style

@conference{icaart23,
author={Alexei Lisitsa and Mateo Salles and Alexei Vernitski},
title={Supervised Learning for Untangling Braids},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={784-789},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011775900003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Supervised Learning for Untangling Braids
SN - 978-989-758-623-1
AU - Lisitsa A.
AU - Salles M.
AU - Vernitski A.
PY - 2023
SP - 784
EP - 789
DO - 10.5220/0011775900003393